gtc2taxid = defaultdict(lambda: defaultdict(set))
for f in sys.argv[1:]:
for l in open(f):
sl = l.split()
gtc = sl[0]
taxid = int(sl[1])
source = sl[2]
if len(sl) > 3:
sourceid = sl[3]
else:
sourceid = None
gtc2taxid[gtc][(source, sourceid)].add(taxid)
allsources.add(source)
for m in w.iterglycan():
start = time.time()
acc = m.get('accession')
for source in allsources:
m.delete_annotations(source=source,
property="Taxonomy",
type="Taxonomy")
for source, sourceid in gtc2taxid[acc]:
m.set_annotation(value=list(gtc2taxid[acc][(source, sourceid)]),
property="Taxonomy",
source=source,
sourceid=sourceid,
type="Taxonomy")
print "\t".join([acc, "Alignment", alignment])
print "\t".join([acc, "MotifGlyTouCan", gtcacc])
print "\t".join([acc, "ReducingEnd", redend])
for i, pmid in enumerate(sorted(pmids, key=int)):
print "\t".join([acc, "PMID", pmid])
for i, kw in enumerate(sorted(keywords)):
print "\t".join([acc, "Keyword", kw])
for i, xr in enumerate(sorted(dbxrefs)):
print "\t".join([acc, "CrossRef", xr])
allmotifdata[acc] = dict(alignment=alignment, label=names[0])
if allmotifs:
sys.exit(0)
print "\t".join(["GlyTouCanAccession", "MotifAccession", "Label", "Alignment"])
for g in w.iterglycan():
acc = g.get('accession')
motifs = set()
for coll in collections:
motifs.update(
map(
itemgetter(0),
filter(lambda t: t[0] in allmotifdata and t[1],
gm.getmotif(coll, acc))))
for motifacc in sorted(motifs):
print "\t".join([
acc, motifacc, allmotifdata[motifacc]['label'],
allmotifdata[motifacc]['alignment']